张恒通

个人简介

我目前是哈尔滨工业大学计算学部的教授。在 2024 年加入哈尔滨工业大学之前，我是腾讯人工智能实验室的高级研究员。我本科毕业于北京邮电大学，并于2020年在纽约州立大学布法罗分校计算机科学与工程系获得博士学位，指导教授是高晶教授。

研究兴趣

• 机器学习安全: training-phase attack/defense, data privacy, model editing
• AI驱动的科学研究 (AI4Science): molecule design, molecule property detection/optimization, equivariant modeling, diffusion models

快讯

• [Mar. 2024] 作为通讯作者的论文发表于 Nature Communications 2024.

代表性著作

(*表示通讯作者)

• Tianci Liu, Haoyu Wang, Feijie Wu, Hengtong Zhang, Pan Li, Lu Su, Jing Gao. Towards poisoning fair representations. ICLR 2024
• Lei Huang, Tingyang Xu, Yang Yu, Peilin Zhao, Xingjian Chen, Jing Han, Zhi Xie, Hailong Li, Wenge Zhong, Ka-Chun Wong, Hengtong Zhang*. A dual diffusion model enables 3D molecule generation and lead optimization based on target pockets. Nature Communications Vol 15 Issue 1. 2024.
• Lei Huang, Hengtong Zhang*, Tingyang Xu, Ka-Chun Wong. MDM: Molecular Diffusion Model for 3D Molecule Generation. AAAI 2023.
• Hengtong Zhang, Yaliang Li, Bolin Ding, Jing Gao. LOKI: A Practical Data Poisoning Attack Framework against Next Item Recommendations. TKDE 2023.
• Hengtong Zhang, Changxin Tian, Yaliang Li, Lu Su, Ning Yang, Wayne Xin Zhao, Jing Gao. Data Poisoning Attack against Recommender System Using Incomplete and Perturbed Data. SIGKDD 2021.
• Hengtong Zhang, Lu Su, Jing Gao. Data poisoning attacks against outcome interpretations of predictive models. SIGKDD 2021.
• Hengtong Zhang, Yaliang Li, Bolin Ding, Jing Gao. Practical data poisoning attack against next-item recommendation. WebConf 2020.
• Hengtong Zhang, Tianhang Zheng, Jing Gao, Chenglin Miao, Lu Su, Yaliang Li, Kui Ren. Data poisoning attack against knowledge graph embedding. IJCAI 2019.

完整论著列表参见 Google Scholar

学术服务

会议审稿人

• ICML, NeurIPS, ICLR, SIGKDD, WWW, AAAI, ACL, IJCAI, CIKM, WSDM 审稿人

期刊审稿人

• Nature Machine Intellegence, Nature Computational Science, Nature Communications, IEEE TKDE, VLDB Journal, WWW Journal 审稿人

Powered by Jekyll and Minimal Light theme.